© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89474
    Prev
    Next
    INDEX
    Explanations

    evidence of long-term engagement and satisfaction with a service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oup
    -0.07
    itted
    -0.07
    inem
    -0.07
    abel
    -0.06
    ien
    -0.06
    rome
    -0.06
    abal
    -0.06
    aim
    -0.06
    raj
    -0.06
    inan
    -0.06
    POSITIVE LOGITS
    always
    0.07
     always
    0.07
     repeat
    0.07
    Always
    0.07
     consistently
    0.07
     overall
    0.07
     siempre
    0.07
     sempre
    0.06
     satisfaction
    0.06
     reliability
    0.06
    Activations Density 0.017%

    No Known Activations